Back to skill

Security audit

neon-auth

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with medium confidence: scanners report no AIG findings and behavior generally aligned with the skill’s authentication purpose, but flagged unpinned tools and the scan was partial.

The verdict is benign, but consider whether you are comfortable running commands that use unpinned packages. Confidence is medium, and coverage is incomplete: the scanner inspected all four listed components, but several local references could not be resolved, so the report does not establish what those references would do.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (11)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
92% confidence
Finding

The only supplied behavior is a skills-management command, which does not itself implement the declared authentication workflows. Although acquiring skills could support a larger setup process, no such authentication process is present in this chunk. Any behavior of subsequently acquired content cannot be established from the supplied code.

Content

No source excerpt is available for this finding.

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/oauth-server.md (reported line 163)May include surrounding context.

md
- Authorization server metadata: `<issuer>/.well-known/oauth-authorization-server` (also `<issuer>/.well-known/openid-configuration`). It lists the authorize, token, and userinfo endpoints, so read them from there.
- JWKS: `<issuer>/.well-known/jwks.json`. Userinfo: `<issuer>/oauth2/userinfo`.
- The MCP server serves protected resource metadata (RFC 9728); `honoMcp` does this.
- Clients must send `resource` on both the authorize and token requests, or the token is opaque and cannot be verified. Access tokens are EdDSA JWTs valid for one hour. Scopes are fixed: `openid`, `profile`, `email`, `offline_access`. Grants are `authorization_code` and `refresh_token`; there is no `client_credentials`.

## 6. Verify

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 21)May include surrounding context.

FIRST: Use the parent neon skill for a Neon overview, getting started with Neon, Neon development best practices, and more.

If the neon skill is not installed, fetch it from https://neon.com/docs/ai/skills/neon/SKILL.md or install it with:

bash
neon skills -s neon -y

MCP server referenced without pinned version: 'npx shadcn'.

Medium
Category
MCP Rug Pull
Confidence
87% confidence
Finding

The suggested npx invocation can download and execute an unpinned shadcn release with the developer's permissions. Although this is a UI generator rather than an MCP server, a compromised release or registry component could execute code or inject malicious authentication components.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx shadcn'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

Using shadcn@latest explicitly selects a mutable release for execution rather than a reviewed version. A compromised release would run with local developer or agent privileges, potentially exposing project secrets or modifying application code.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx shadcn'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

This command executes a mutable shadcn release and imports externally maintained authentication components. Compromise of either dependency can introduce code into a security-sensitive login flow; the tool is not an MCP server, but the supply-chain concern is valid.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx shadcn'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The optional user-button installation also executes shadcn@latest and copies remote component code into the application. Its optional status does not remove the possibility of local code execution or malicious application changes through a compromised dependency.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx shadcn'.

Medium
Category
MCP Rug Pull
Confidence
84% confidence
Finding

This prose refers back to the unpinned shadcn execution workflow rather than introducing a separate MCP server. The subsequent Better Auth version adjustment does not protect against malicious CLI execution or compromised registry components during the earlier commands.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/oauth-server.md (reported line 23)May include surrounding context.

--mcp-resource https://mcp.example.com/mcp

A non-MCP API instead (or as well)

neon neon-auth config oauth-server resource add https://api.example.com/reports

neon neon-auth config oauth-server get

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/oauth-server.md (reported line 42)May include surrounding context.

bash
neon neon-auth oauth-client create --name "Reports" --type confidential \
  --redirect-uris https://reports.example.com/callback \
  --resources https://api.example.com/reports

neon neon-auth oauth-client list
neon neon-auth oauth-client get <client-id>

MCP server referenced without pinned version: 'npx @modelcontextprotocol/inspector'.

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding

The verification instructions execute an unpinned MCP Inspector package through npx. A compromised release could execute with developer permissions and potentially capture credentials or tokens used during the authentication test.

Content

No source excerpt is available for this finding.